Merge tag 'for-f2fs-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, there is no special interesting feature, but we've
  investigated a couple of tuning points with respect to the I/O flow.
  Several major bug fixes and a bunch of clean-ups also have been made.

  This patch-set includes the following major enhancement patches:
   - enhance wait_on_page_writeback
   - support SEEK_DATA and SEEK_HOLE
   - enhance readahead flows
   - enhance IO flushes
   - support fiemap
   - add some tracepoints

  The other bug fixes are as follows:
   - fix to support a large volume > 2TB correctly
   - recovery bug fix wrt fallocated space
   - fix recursive lock on xattr operations
   - fix some cases on the remount flow

  And, there are a bunch of cleanups"

* tag 'for-f2fs-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (52 commits)
  f2fs: support f2fs_fiemap
  f2fs: avoid not to call remove_dirty_inode
  f2fs: recover fallocated space
  f2fs: fix to recover data written by dio
  f2fs: large volume support
  f2fs: avoid crash when trace f2fs_submit_page_mbio event in ra_sum_pages
  f2fs: avoid overflow when large directory feathure is enabled
  f2fs: fix recursive lock by f2fs_setxattr
  MAINTAINERS: add a co-maintainer from samsung for F2FS
  MAINTAINERS: change the email address for f2fs
  f2fs: use inode_init_owner() to simplify codes
  f2fs: avoid to use slab memory in f2fs_issue_flush for efficiency
  f2fs: add a tracepoint for f2fs_read_data_page
  f2fs: add a tracepoint for f2fs_write_{meta,node,data}_pages
  f2fs: add a tracepoint for f2fs_write_{meta,node,data}_page
  f2fs: add a tracepoint for f2fs_write_end
  f2fs: add a tracepoint for f2fs_write_begin
  f2fs: fix checkpatch warning
  f2fs: deactivate inode page if the inode is evicted
  f2fs: decrease the lock granularity during write_begin
  ...

Documentation/filesystems/f2fs.txt

@@ -461,11 +461,11 @@ The number of blocks and buckets are determined by,
   # of blocks in level #n = |
                             `- 4, Otherwise
 
-                             ,- 2^ (n + dir_level),
-			     |            if n < MAX_DIR_HASH_DEPTH / 2,
+                             ,- 2^(n + dir_level),
+			     |        if n + dir_level < MAX_DIR_HASH_DEPTH / 2,
   # of buckets in level #n = |
-                             `- 2^((MAX_DIR_HASH_DEPTH / 2 + dir_level) - 1),
-			                  Otherwise
+                             `- 2^((MAX_DIR_HASH_DEPTH / 2) - 1),
+			              Otherwise
 
 When F2FS finds a file name in a directory, at first a hash value of the file
 name is calculated. Then, F2FS scans the hash table in level #0 to find the

MAINTAINERS

@@ -3792,7 +3792,8 @@ F:	fs/fscache/
 F:	include/linux/fscache*.h
 
 F2FS FILE SYSTEM
-M:	Jaegeuk Kim <jaegeuk.kim@samsung.com>
+M:	Jaegeuk Kim <jaegeuk@kernel.org>
+M:	Changman Lee <cm224.lee@samsung.com>
 L:	linux-f2fs-devel@lists.sourceforge.net
 W:	http://en.wikipedia.org/wiki/F2FS
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git

fs/f2fs/acl.c

@@ -240,7 +240,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 		}
 	}
 
-	error = f2fs_setxattr(inode, name_index, "", value, size, ipage);
+	error = f2fs_setxattr(inode, name_index, "", value, size, ipage, 0);
 
 	kfree(value);
 	if (!error)

fs/f2fs/checkpoint.c

@@ -33,12 +33,12 @@ struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	struct address_space *mapping = META_MAPPING(sbi);
 	struct page *page = NULL;
 repeat:
-	page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+	page = grab_cache_page(mapping, index);
 	if (!page) {
 		cond_resched();
 		goto repeat;
 	}
-
+	f2fs_wait_on_page_writeback(page, META);
 	SetPageUptodate(page);
 	return page;
 }
@@ -72,7 +72,7 @@ out:
 	return page;
 }
 
-inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
+static inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
 {
 	switch (type) {
 	case META_NAT:
@@ -154,6 +154,8 @@ static int f2fs_write_meta_page(struct page *page,
 	struct inode *inode = page->mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 
+	trace_f2fs_writepage(page, META);
+
 	if (unlikely(sbi->por_doing))
 		goto redirty_out;
 	if (wbc->for_reclaim)
@@ -171,10 +173,7 @@ no_write:
 	return 0;
 
 redirty_out:
-	dec_page_count(sbi, F2FS_DIRTY_META);
-	wbc->pages_skipped++;
-	account_page_redirty(page);
-	set_page_dirty(page);
+	redirty_page_for_writepage(wbc, page);
 	return AOP_WRITEPAGE_ACTIVATE;
 }
 
@@ -184,6 +183,8 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
 	long diff, written;
 
+	trace_f2fs_writepages(mapping->host, wbc, META);
+
 	/* collect a number of dirty meta pages and write together */
 	if (wbc->for_kupdate ||
 		get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
@@ -367,7 +368,9 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
 		return;
 
 	sbi->por_doing = true;
-	start_blk = __start_cp_addr(sbi) + 1;
+
+	start_blk = __start_cp_addr(sbi) + 1 +
+		le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
 	orphan_blkaddr = __start_sum_addr(sbi) - 1;
 
 	ra_meta_pages(sbi, start_blk, orphan_blkaddr, META_CP);
@@ -508,8 +511,11 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	unsigned long blk_size = sbi->blocksize;
 	unsigned long long cp1_version = 0, cp2_version = 0;
 	unsigned long long cp_start_blk_no;
+	unsigned int cp_blks = 1 + le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
+	block_t cp_blk_no;
+	int i;
 
-	sbi->ckpt = kzalloc(blk_size, GFP_KERNEL);
+	sbi->ckpt = kzalloc(cp_blks * blk_size, GFP_KERNEL);
 	if (!sbi->ckpt)
 		return -ENOMEM;
 	/*
@@ -540,6 +546,23 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
 	memcpy(sbi->ckpt, cp_block, blk_size);
 
+	if (cp_blks <= 1)
+		goto done;
+
+	cp_blk_no = le32_to_cpu(fsb->cp_blkaddr);
+	if (cur_page == cp2)
+		cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);
+
+	for (i = 1; i < cp_blks; i++) {
+		void *sit_bitmap_ptr;
+		unsigned char *ckpt = (unsigned char *)sbi->ckpt;
+
+		cur_page = get_meta_page(sbi, cp_blk_no + i);
+		sit_bitmap_ptr = page_address(cur_page);
+		memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
+		f2fs_put_page(cur_page, 1);
+	}
+done:
 	f2fs_put_page(cp1, 1);
 	f2fs_put_page(cp2, 1);
 	return 0;
@@ -552,14 +575,13 @@ fail_no_cp:
 static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-	struct list_head *head = &sbi->dir_inode_list;
-	struct dir_inode_entry *entry;
 
-	list_for_each_entry(entry, head, list)
-		if (unlikely(entry->inode == inode))
-			return -EEXIST;
+	if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR))
+		return -EEXIST;
 
-	list_add_tail(&new->list, head);
+	set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
+	F2FS_I(inode)->dirty_dir = new;
+	list_add_tail(&new->list, &sbi->dir_inode_list);
 	stat_inc_dirty_dir(sbi);
 	return 0;
 }
@@ -608,31 +630,26 @@ void add_dirty_dir_inode(struct inode *inode)
 void remove_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-	struct list_head *head;
 	struct dir_inode_entry *entry;
 
 	if (!S_ISDIR(inode->i_mode))
 		return;
 
 	spin_lock(&sbi->dir_inode_lock);
-	if (get_dirty_dents(inode)) {
+	if (get_dirty_dents(inode) ||
+			!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) {
 		spin_unlock(&sbi->dir_inode_lock);
 		return;
 	}
 
-	head = &sbi->dir_inode_list;
-	list_for_each_entry(entry, head, list) {
-		if (entry->inode == inode) {
-			list_del(&entry->list);
-			stat_dec_dirty_dir(sbi);
-			spin_unlock(&sbi->dir_inode_lock);
-			kmem_cache_free(inode_entry_slab, entry);
-			goto done;
-		}
-	}
+	entry = F2FS_I(inode)->dirty_dir;
+	list_del(&entry->list);
+	F2FS_I(inode)->dirty_dir = NULL;
+	clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
+	stat_dec_dirty_dir(sbi);
 	spin_unlock(&sbi->dir_inode_lock);
+	kmem_cache_free(inode_entry_slab, entry);
 
-done:
 	/* Only from the recovery routine */
 	if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
 		clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
@@ -640,26 +657,6 @@ done:
 	}
 }
 
-struct inode *check_dirty_dir_inode(struct f2fs_sb_info *sbi, nid_t ino)
-{
-
-	struct list_head *head;
-	struct inode *inode = NULL;
-	struct dir_inode_entry *entry;
-
-	spin_lock(&sbi->dir_inode_lock);
-
-	head = &sbi->dir_inode_list;
-	list_for_each_entry(entry, head, list) {
-		if (entry->inode->i_ino == ino) {
-			inode = entry->inode;
-			break;
-		}
-	}
-	spin_unlock(&sbi->dir_inode_lock);
-	return inode;
-}
-
 void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
 {
 	struct list_head *head;
@@ -758,6 +755,13 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	__u32 crc32 = 0;
 	void *kaddr;
 	int i;
+	int cp_payload_blks = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
+
+	/*
+	 * This avoids to conduct wrong roll-forward operations and uses
+	 * metapages, so should be called prior to sync_meta_pages below.
+	 */
+	discard_next_dnode(sbi);
 
 	/* Flush all the NAT/SIT pages */
 	while (get_pages(sbi, F2FS_DIRTY_META))
@@ -802,16 +806,19 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 
 	orphan_blocks = (sbi->n_orphans + F2FS_ORPHANS_PER_BLOCK - 1)
 					/ F2FS_ORPHANS_PER_BLOCK;
-	ckpt->cp_pack_start_sum = cpu_to_le32(1 + orphan_blocks);
+	ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
+			orphan_blocks);
 
 	if (is_umount) {
 		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
 		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
-			data_sum_blocks + orphan_blocks + NR_CURSEG_NODE_TYPE);
+				cp_payload_blks + data_sum_blocks +
+				orphan_blocks + NR_CURSEG_NODE_TYPE);
 	} else {
 		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
 		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
-			data_sum_blocks + orphan_blocks);
+				cp_payload_blks + data_sum_blocks +
+				orphan_blocks);
 	}
 
 	if (sbi->n_orphans)
@@ -837,6 +844,15 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	set_page_dirty(cp_page);
 	f2fs_put_page(cp_page, 1);
 
+	for (i = 1; i < 1 + cp_payload_blks; i++) {
+		cp_page = grab_meta_page(sbi, start_blk++);
+		kaddr = page_address(cp_page);
+		memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE,
+				(1 << sbi->log_blocksize));
+		set_page_dirty(cp_page);
+		f2fs_put_page(cp_page, 1);
+	}
+
 	if (sbi->n_orphans) {
 		write_orphan_inodes(sbi, start_blk);
 		start_blk += orphan_blocks;

fs/f2fs/data.c

@@ -417,7 +417,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 	if (unlikely(dn.data_blkaddr == NEW_ADDR))
 		return ERR_PTR(-EINVAL);
 
-	page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+	page = grab_cache_page(mapping, index);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -455,7 +455,7 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	int err;
 
 repeat:
-	page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+	page = grab_cache_page(mapping, index);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -652,8 +652,7 @@ static int get_data_block(struct inode *inode, sector_t iblock,
 		goto put_out;
 	}
 
-	end_offset = IS_INODE(dn.node_page) ?
-			ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+	end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
 	bh_result->b_size = (((size_t)1) << blkbits);
 	dn.ofs_in_node++;
 	pgofs++;
@@ -675,8 +674,7 @@ get_next:
 		if (dn.data_blkaddr == NEW_ADDR)
 			goto put_out;
 
-		end_offset = IS_INODE(dn.node_page) ?
-			ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
 	}
 
 	if (maxblocks > (bh_result->b_size >> blkbits)) {
@@ -710,11 +708,19 @@ out:
 	return err;
 }
 
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		u64 start, u64 len)
+{
+	return generic_block_fiemap(inode, fieinfo, start, len, get_data_block);
+}
+
 static int f2fs_read_data_page(struct file *file, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	int ret;
 
+	trace_f2fs_readpage(page, DATA);
+
 	/* If the file has inline data, try to read it directlly */
 	if (f2fs_has_inline_data(inode))
 		ret = f2fs_read_inline_data(inode, page);
@@ -790,6 +796,8 @@ static int f2fs_write_data_page(struct page *page,
 		.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
 	};
 
+	trace_f2fs_writepage(page, DATA);
+
 	if (page->index < end_index)
 		goto write;
 
@@ -798,10 +806,8 @@ static int f2fs_write_data_page(struct page *page,
 	 * this page does not have to be written to disk.
 	 */
 	offset = i_size & (PAGE_CACHE_SIZE - 1);
-	if ((page->index >= end_index + 1) || !offset) {
-		inode_dec_dirty_dents(inode);
+	if ((page->index >= end_index + 1) || !offset)
 		goto out;
-	}
 
 	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
 write:
@@ -810,7 +816,6 @@ write:
 
 	/* Dentry blocks are controlled by checkpoint */
 	if (S_ISDIR(inode->i_mode)) {
-		inode_dec_dirty_dents(inode);
 		err = do_write_data_page(page, &fio);
 		goto done;
 	}
@@ -832,15 +837,16 @@ done:
 
 	clear_cold_data(page);
 out:
+	inode_dec_dirty_dents(inode);
 	unlock_page(page);
 	if (need_balance_fs)
 		f2fs_balance_fs(sbi);
+	if (wbc->for_reclaim)
+		f2fs_submit_merged_bio(sbi, DATA, WRITE);
 	return 0;
 
 redirty_out:
-	wbc->pages_skipped++;
-	account_page_redirty(page);
-	set_page_dirty(page);
+	redirty_page_for_writepage(wbc, page);
 	return AOP_WRITEPAGE_ACTIVATE;
 }
 
@@ -862,12 +868,15 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	int ret;
 	long diff;
 
+	trace_f2fs_writepages(mapping->host, wbc, DATA);
+
 	/* deal with chardevs and other special file */
 	if (!mapping->a_ops->writepage)
 		return 0;
 
 	if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
-			get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA))
+			get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA) &&
+			available_free_memory(sbi, DIRTY_DENTS))
 		goto skip_write;
 
 	diff = nr_pages_to_write(sbi, DATA, wbc);
@@ -903,6 +912,8 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	struct dnode_of_data dn;
 	int err = 0;
 
+	trace_f2fs_write_begin(inode, pos, len, flags);
+
 	f2fs_balance_fs(sbi);
 repeat:
 	err = f2fs_convert_inline_data(inode, pos + len);
@@ -912,6 +923,10 @@ repeat:
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
+
+	/* to avoid latency during memory pressure */
+	unlock_page(page);
+
 	*pagep = page;
 
 	if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA)
@@ -923,10 +938,18 @@ repeat:
 	f2fs_unlock_op(sbi);
 
 	if (err) {
-		f2fs_put_page(page, 1);
+		f2fs_put_page(page, 0);
 		return err;
 	}
 inline_data:
+	lock_page(page);
+	if (unlikely(page->mapping != mapping)) {
+		f2fs_put_page(page, 1);
+		goto repeat;
+	}
+
+	f2fs_wait_on_page_writeback(page, DATA);
+
 	if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
 		return 0;
 
@@ -978,6 +1001,8 @@ static int f2fs_write_end(struct file *file,
 {
 	struct inode *inode = page->mapping->host;
 
+	trace_f2fs_write_end(inode, pos, len, copied);
+
 	SetPageUptodate(page);
 	set_page_dirty(page);
 
@@ -1022,6 +1047,9 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 	if (check_direct_IO(inode, rw, iov, offset, nr_segs))
 		return 0;
 
+	/* clear fsync mark to recover these blocks */
+	fsync_mark_clear(F2FS_SB(inode->i_sb), inode->i_ino);
+
 	return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
 							get_data_block);
 }
@@ -1061,6 +1089,11 @@ static int f2fs_set_data_page_dirty(struct page *page)
 
 static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
 {
+	struct inode *inode = mapping->host;
+
+	if (f2fs_has_inline_data(inode))
+		return 0;
+
 	return generic_block_bmap(mapping, block, get_data_block);
 }
 

fs/f2fs/dir.c

@@ -23,10 +23,10 @@ static unsigned long dir_blocks(struct inode *inode)
 
 static unsigned int dir_buckets(unsigned int level, int dir_level)
 {
-	if (level < MAX_DIR_HASH_DEPTH / 2)
+	if (level + dir_level < MAX_DIR_HASH_DEPTH / 2)
 		return 1 << (level + dir_level);
 	else
-		return 1 << ((MAX_DIR_HASH_DEPTH / 2 + dir_level) - 1);
+		return MAX_DIR_BUCKETS;
 }
 
 static unsigned int bucket_blocks(unsigned int level)
@@ -268,6 +268,8 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
 {
 	struct f2fs_inode *ri;
 
+	f2fs_wait_on_page_writeback(ipage, NODE);
+
 	/* copy name info. to this inode page */
 	ri = F2FS_INODE(ipage);
 	ri->i_namelen = cpu_to_le32(name->len);
@@ -637,11 +639,17 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	struct f2fs_dir_entry *de = NULL;
 	struct page *dentry_page = NULL;
+	struct file_ra_state *ra = &file->f_ra;
 	unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
 	unsigned char d_type = DT_UNKNOWN;
 
 	bit_pos = ((unsigned long)ctx->pos % NR_DENTRY_IN_BLOCK);
 
+	/* readahead for multi pages of dir */
+	if (npages - n > 1 && !ra_has_index(ra, n))
+		page_cache_sync_readahead(inode->i_mapping, ra, file, n,
+				min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
+
 	for (; n < npages; n++) {
 		dentry_page = get_lock_data_page(inode, n);
 		if (IS_ERR(dentry_page))

fs/f2fs/f2fs.h

@@ -182,6 +182,8 @@ enum {
 
 #define F2FS_LINK_MAX		32000	/* maximum link count per file */
 
+#define MAX_DIR_RA_PAGES	4	/* maximum ra pages of dir */
+
 /* for in-memory extent cache entry */
 #define F2FS_MIN_EXTENT_LEN	16	/* minimum extent length */
 
@@ -218,6 +220,7 @@ struct f2fs_inode_info {
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	unsigned long long xattr_ver;	/* cp version of xattr modification */
 	struct extent_info ext;		/* in-memory extent cache entry */
+	struct dir_inode_entry *dirty_dir;	/* the pointer of dirty dir */
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -243,6 +246,7 @@ static inline void set_raw_extent(struct extent_info *ext,
 struct f2fs_nm_info {
 	block_t nat_blkaddr;		/* base disk address of NAT */
 	nid_t max_nid;			/* maximum possible node ids */
+	nid_t available_nids;		/* maximum available node ids */
 	nid_t next_scan_nid;		/* the next nid to be scanned */
 	unsigned int ram_thresh;	/* control the memory footprint */
 
@@ -323,6 +327,15 @@ struct flush_cmd {
 	int ret;
 };
 
+struct flush_cmd_control {
+	struct task_struct *f2fs_issue_flush;	/* flush thread */
+	wait_queue_head_t flush_wait_queue;	/* waiting queue for wake-up */
+	struct flush_cmd *issue_list;		/* list for command issue */
+	struct flush_cmd *dispatch_list;	/* list for command dispatch */
+	spinlock_t issue_lock;			/* for issue list lock */
+	struct flush_cmd *issue_tail;		/* list tail of issue list */
+};
+
 struct f2fs_sm_info {
 	struct sit_info *sit_info;		/* whole segment information */
 	struct free_segmap_info *free_info;	/* free segment information */
@@ -353,12 +366,8 @@ struct f2fs_sm_info {
 	unsigned int min_ipu_util;	/* in-place-update threshold */
 
 	/* for flush command control */
-	struct task_struct *f2fs_issue_flush;	/* flush thread */
-	wait_queue_head_t flush_wait_queue;	/* waiting queue for wake-up */
-	struct flush_cmd *issue_list;		/* list for command issue */
-	struct flush_cmd *dispatch_list;	/* list for command dispatch */
-	spinlock_t issue_lock;			/* for issue list lock */
-	struct flush_cmd *issue_tail;		/* list tail of issue list */
+	struct flush_cmd_control *cmd_control_info;
+
 };
 
 /*
@@ -755,9 +764,18 @@ static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag)
 static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	int offset = (flag == NAT_BITMAP) ?
+	int offset;
+
+	if (le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload) > 0) {
+		if (flag == NAT_BITMAP)
+			return &ckpt->sit_nat_version_bitmap;
+		else
+			return ((unsigned char *)ckpt + F2FS_BLKSIZE);
+	} else {
+		offset = (flag == NAT_BITMAP) ?
 			le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
-	return &ckpt->sit_nat_version_bitmap + offset;
+		return &ckpt->sit_nat_version_bitmap + offset;
+	}
 }
 
 static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
@@ -958,6 +976,7 @@ static inline int f2fs_clear_bit(unsigned int nr, char *addr)
 enum {
 	FI_NEW_INODE,		/* indicate newly allocated inode */
 	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
+	FI_DIRTY_DIR,		/* indicate directory has dirty pages */
 	FI_INC_LINK,		/* need to increment i_nlink */
 	FI_ACL_MODE,		/* indicate acl mode */
 	FI_NO_ALLOC,		/* should not allocate any blocks */
@@ -1071,6 +1090,12 @@ static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi)
 	((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
 
+/* get offset of first page in next direct node */
+#define PGOFS_OF_NEXT_DNODE(pgofs, fi)				\
+	((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) :	\
+	(pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) /	\
+	ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
+
 /*
  * file.c
  */
@@ -1140,8 +1165,10 @@ f2fs_hash_t f2fs_dentry_hash(const char *, size_t);
 struct dnode_of_data;
 struct node_info;
 
+bool available_free_memory(struct f2fs_sb_info *, int);
 int is_checkpointed_node(struct f2fs_sb_info *, nid_t);
 bool fsync_mark_done(struct f2fs_sb_info *, nid_t);
+void fsync_mark_clear(struct f2fs_sb_info *, nid_t);
 void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
 int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
 int truncate_inode_blocks(struct inode *, pgoff_t);
@@ -1176,9 +1203,12 @@ void destroy_node_manager_caches(void);
 void f2fs_balance_fs(struct f2fs_sb_info *);
 void f2fs_balance_fs_bg(struct f2fs_sb_info *);
 int f2fs_issue_flush(struct f2fs_sb_info *);
+int create_flush_cmd_control(struct f2fs_sb_info *);
+void destroy_flush_cmd_control(struct f2fs_sb_info *);
 void invalidate_blocks(struct f2fs_sb_info *, block_t);
 void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
 void clear_prefree_segments(struct f2fs_sb_info *);
+void discard_next_dnode(struct f2fs_sb_info *);
 int npages_for_summary_flush(struct f2fs_sb_info *);
 void allocate_new_segments(struct f2fs_sb_info *);
 struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
@@ -1221,7 +1251,6 @@ int get_valid_checkpoint(struct f2fs_sb_info *);
 void set_dirty_dir_page(struct inode *, struct page *);
 void add_dirty_dir_inode(struct inode *);
 void remove_dirty_dir_inode(struct inode *);
-struct inode *check_dirty_dir_inode(struct f2fs_sb_info *, nid_t);
 void sync_dirty_dir_inodes(struct f2fs_sb_info *);
 void write_checkpoint(struct f2fs_sb_info *, bool);
 void init_orphan_info(struct f2fs_sb_info *);
@@ -1242,6 +1271,7 @@ struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
 struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
 int do_write_data_page(struct page *, struct f2fs_io_info *);
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
 
 /*
  * gc.c
@@ -1391,5 +1421,6 @@ bool f2fs_may_inline(struct inode *);
 int f2fs_read_inline_data(struct inode *, struct page *);
 int f2fs_convert_inline_data(struct inode *, pgoff_t);
 int f2fs_write_inline_data(struct inode *, struct page *, unsigned int);
+void truncate_inline_data(struct inode *, u64);
 int recover_inline_data(struct inode *, struct page *);
 #endif

fs/f2fs/file.c

@@ -19,6 +19,7 @@
 #include <linux/compat.h>
 #include <linux/uaccess.h>
 #include <linux/mount.h>
+#include <linux/pagevec.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -194,6 +195,132 @@ out:
 	return ret;
 }
 
+static pgoff_t __get_first_dirty_index(struct address_space *mapping,
+						pgoff_t pgofs, int whence)
+{
+	struct pagevec pvec;
+	int nr_pages;
+
+	if (whence != SEEK_DATA)
+		return 0;
+
+	/* find first dirty page index */
+	pagevec_init(&pvec, 0);
+	nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs, PAGECACHE_TAG_DIRTY, 1);
+	pgofs = nr_pages ? pvec.pages[0]->index: LONG_MAX;
+	pagevec_release(&pvec);
+	return pgofs;
+}
+
+static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
+							int whence)
+{
+	switch (whence) {
+	case SEEK_DATA:
+		if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
+			(blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
+			return true;
+		break;
+	case SEEK_HOLE:
+		if (blkaddr == NULL_ADDR)
+			return true;
+		break;
+	}
+	return false;
+}
+
+static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t maxbytes = inode->i_sb->s_maxbytes;
+	struct dnode_of_data dn;
+	pgoff_t pgofs, end_offset, dirty;
+	loff_t data_ofs = offset;
+	loff_t isize;
+	int err = 0;
+
+	mutex_lock(&inode->i_mutex);
+
+	isize = i_size_read(inode);
+	if (offset >= isize)
+		goto fail;
+
+	/* handle inline data case */
+	if (f2fs_has_inline_data(inode)) {
+		if (whence == SEEK_HOLE)
+			data_ofs = isize;
+		goto found;
+	}
+
+	pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);
+
+	dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
+
+	for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
+		if (err && err != -ENOENT) {
+			goto fail;
+		} else if (err == -ENOENT) {
+			/* direct node is not exist */
+			if (whence == SEEK_DATA) {
+				pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
+							F2FS_I(inode));
+				continue;
+			} else {
+				goto found;
+			}
+		}
+
+		end_offset = IS_INODE(dn.node_page) ?
+			ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+
+		/* find data/hole in dnode block */
+		for (; dn.ofs_in_node < end_offset;
+				dn.ofs_in_node++, pgofs++,
+				data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+			block_t blkaddr;
+			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+
+			if (__found_offset(blkaddr, dirty, pgofs, whence)) {
+				f2fs_put_dnode(&dn);
+				goto found;
+			}
+		}
+		f2fs_put_dnode(&dn);
+	}
+
+	if (whence == SEEK_DATA)
+		goto fail;
+found:
+	if (whence == SEEK_HOLE && data_ofs > isize)
+		data_ofs = isize;
+	mutex_unlock(&inode->i_mutex);
+	return vfs_setpos(file, data_ofs, maxbytes);
+fail:
+	mutex_unlock(&inode->i_mutex);
+	return -ENXIO;
+}
+
+static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t maxbytes = inode->i_sb->s_maxbytes;
+
+	switch (whence) {
+	case SEEK_SET:
+	case SEEK_CUR:
+	case SEEK_END:
+		return generic_file_llseek_size(file, offset, whence,
+						maxbytes, i_size_read(inode));
+	case SEEK_DATA:
+	case SEEK_HOLE:
+		return f2fs_seek_block(file, offset, whence);
+	}
+
+	return -EINVAL;
+}
+
 static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	file_accessed(file);
@@ -242,6 +369,9 @@ static void truncate_partial_data_page(struct inode *inode, u64 from)
 	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
 	struct page *page;
 
+	if (f2fs_has_inline_data(inode))
+		return truncate_inline_data(inode, from);
+
 	if (!offset)
 		return;
 
@@ -288,10 +418,7 @@ int truncate_blocks(struct inode *inode, u64 from)
 		return err;
 	}
 
-	if (IS_INODE(dn.node_page))
-		count = ADDRS_PER_INODE(F2FS_I(inode));
-	else
-		count = ADDRS_PER_BLOCK;
+	count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
 
 	count -= dn.ofs_in_node;
 	f2fs_bug_on(count < 0);
@@ -413,6 +540,7 @@ const struct inode_operations f2fs_file_inode_operations = {
 	.listxattr	= f2fs_listxattr,
 	.removexattr	= generic_removexattr,
 #endif
+	.fiemap		= f2fs_fiemap,
 };
 
 static void fill_zero(struct inode *inode, pgoff_t index,
@@ -555,6 +683,7 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 		i_size_read(inode) < new_size) {
 		i_size_write(inode, new_size);
 		mark_inode_dirty(inode);
+		f2fs_write_inode(inode, NULL);
 	}
 
 	return ret;
@@ -678,7 +807,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 #endif
 
 const struct file_operations f2fs_file_operations = {
-	.llseek		= generic_file_llseek,
+	.llseek		= f2fs_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.aio_read	= generic_file_aio_read,

fs/f2fs/inline.c

@@ -81,8 +81,10 @@ static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
 
 	f2fs_lock_op(sbi);
 	ipage = get_node_page(sbi, inode->i_ino);
-	if (IS_ERR(ipage))
-		return PTR_ERR(ipage);
+	if (IS_ERR(ipage)) {
+		err = PTR_ERR(ipage);
+		goto out;
+	}
 
 	/*
 	 * i_addr[0] is not used for inline data,
@@ -90,11 +92,10 @@ static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
 	 */
 	set_new_dnode(&dn, inode, ipage, NULL, 0);
 	err = f2fs_reserve_block(&dn, 0);
-	if (err) {
-		f2fs_unlock_op(sbi);
-		return err;
-	}
+	if (err)
+		goto out;
 
+	f2fs_wait_on_page_writeback(page, DATA);
 	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
 
 	/* Copy the whole inline data block */
@@ -118,6 +119,7 @@ static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
 
 	sync_inode_page(&dn);
 	f2fs_put_dnode(&dn);
+out:
 	f2fs_unlock_op(sbi);
 	return err;
 }
@@ -132,7 +134,7 @@ int f2fs_convert_inline_data(struct inode *inode, pgoff_t to_size)
 	else if (to_size <= MAX_INLINE_DATA)
 		return 0;
 
-	page = grab_cache_page_write_begin(inode->i_mapping, 0, AOP_FLAG_NOFS);
+	page = grab_cache_page(inode->i_mapping, 0);
 	if (!page)
 		return -ENOMEM;
 
@@ -155,6 +157,7 @@ int f2fs_write_inline_data(struct inode *inode,
 		return err;
 	ipage = dn.inode_page;
 
+	f2fs_wait_on_page_writeback(ipage, NODE);
 	zero_user_segment(ipage, INLINE_DATA_OFFSET,
 				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
 	src_addr = kmap(page);
@@ -175,6 +178,26 @@ int f2fs_write_inline_data(struct inode *inode,
 	return 0;
 }
 
+void truncate_inline_data(struct inode *inode, u64 from)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct page *ipage;
+
+	if (from >= MAX_INLINE_DATA)
+		return;
+
+	ipage = get_node_page(sbi, inode->i_ino);
+	if (IS_ERR(ipage))
+		return;
+
+	f2fs_wait_on_page_writeback(ipage, NODE);
+
+	zero_user_segment(ipage, INLINE_DATA_OFFSET + from,
+				INLINE_DATA_OFFSET + MAX_INLINE_DATA);
+	set_page_dirty(ipage);
+	f2fs_put_page(ipage, 1);
+}
+
 int recover_inline_data(struct inode *inode, struct page *npage)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
@@ -199,6 +222,8 @@ process_inline:
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(IS_ERR(ipage));
 
+		f2fs_wait_on_page_writeback(ipage, NODE);
+
 		src_addr = inline_data_addr(npage);
 		dst_addr = inline_data_addr(ipage);
 		memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
@@ -210,6 +235,7 @@ process_inline:
 	if (f2fs_has_inline_data(inode)) {
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(IS_ERR(ipage));
+		f2fs_wait_on_page_writeback(ipage, NODE);
 		zero_user_segment(ipage, INLINE_DATA_OFFSET,
 				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
 		clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);

fs/f2fs/inode.c

@@ -12,6 +12,7 @@
 #include <linux/f2fs_fs.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
+#include <linux/bitops.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -21,20 +22,20 @@
 void f2fs_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = F2FS_I(inode)->i_flags;
-
-	inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE |
-			S_NOATIME | S_DIRSYNC);
+	unsigned int new_fl = 0;
 
 	if (flags & FS_SYNC_FL)
-		inode->i_flags |= S_SYNC;
+		new_fl |= S_SYNC;
 	if (flags & FS_APPEND_FL)
-		inode->i_flags |= S_APPEND;
+		new_fl |= S_APPEND;
 	if (flags & FS_IMMUTABLE_FL)
-		inode->i_flags |= S_IMMUTABLE;
+		new_fl |= S_IMMUTABLE;
 	if (flags & FS_NOATIME_FL)
-		inode->i_flags |= S_NOATIME;
+		new_fl |= S_NOATIME;
 	if (flags & FS_DIRSYNC_FL)
-		inode->i_flags |= S_DIRSYNC;
+		new_fl |= S_DIRSYNC;
+	set_mask_bits(&inode->i_flags,
+			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
 }
 
 static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -294,4 +295,5 @@ void f2fs_evict_inode(struct inode *inode)
 	sb_end_intwrite(inode->i_sb);
 no_delete:
 	clear_inode(inode);
+	invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
 }

fs/f2fs/namei.c

@@ -41,18 +41,9 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	}
 	f2fs_unlock_op(sbi);
 
-	inode->i_uid = current_fsuid();
-
-	if (dir->i_mode & S_ISGID) {
-		inode->i_gid = dir->i_gid;
-		if (S_ISDIR(mode))
-			mode |= S_ISGID;
-	} else {
-		inode->i_gid = current_fsgid();
-	}
+	inode_init_owner(inode, dir, mode);
 
 	inode->i_ino = ino;
-	inode->i_mode = mode;
 	inode->i_blocks = 0;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	inode->i_generation = sbi->s_next_generation++;

fs/f2fs/node.c

@@ -26,20 +26,26 @@
 static struct kmem_cache *nat_entry_slab;
 static struct kmem_cache *free_nid_slab;
 
-static inline bool available_free_memory(struct f2fs_nm_info *nm_i, int type)
+bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct sysinfo val;
 	unsigned long mem_size = 0;
+	bool res = false;
 
 	si_meminfo(&val);
-	if (type == FREE_NIDS)
-		mem_size = nm_i->fcnt * sizeof(struct free_nid);
-	else if (type == NAT_ENTRIES)
-		mem_size += nm_i->nat_cnt * sizeof(struct nat_entry);
-	mem_size >>= 12;
-
-	/* give 50:50 memory for free nids and nat caches respectively */
-	return (mem_size < ((val.totalram * nm_i->ram_thresh) >> 11));
+	/* give 25%, 25%, 50% memory for each components respectively */
+	if (type == FREE_NIDS) {
+		mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> 12;
+		res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
+	} else if (type == NAT_ENTRIES) {
+		mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12;
+		res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
+	} else if (type == DIRTY_DENTS) {
+		mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
+		res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1);
+	}
+	return res;
 }
 
 static void clear_node_page_dirty(struct page *page)
@@ -147,6 +153,18 @@ bool fsync_mark_done(struct f2fs_sb_info *sbi, nid_t nid)
 	return fsync_done;
 }
 
+void fsync_mark_clear(struct f2fs_sb_info *sbi, nid_t nid)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	struct nat_entry *e;
+
+	write_lock(&nm_i->nat_tree_lock);
+	e = __lookup_nat_cache(nm_i, nid);
+	if (e)
+		e->fsync_done = false;
+	write_unlock(&nm_i->nat_tree_lock);
+}
+
 static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
 {
 	struct nat_entry *new;
@@ -179,9 +197,7 @@ retry:
 			write_unlock(&nm_i->nat_tree_lock);
 			goto retry;
 		}
-		nat_set_blkaddr(e, le32_to_cpu(ne->block_addr));
-		nat_set_ino(e, le32_to_cpu(ne->ino));
-		nat_set_version(e, ne->version);
+		node_info_from_raw_nat(&e->ni, ne);
 	}
 	write_unlock(&nm_i->nat_tree_lock);
 }
@@ -243,7 +259,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
-	if (available_free_memory(nm_i, NAT_ENTRIES))
+	if (available_free_memory(sbi, NAT_ENTRIES))
 		return 0;
 
 	write_lock(&nm_i->nat_tree_lock);
@@ -849,8 +865,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return ERR_PTR(-EPERM);
 
-	page = grab_cache_page_write_begin(NODE_MAPPING(sbi),
-					dn->nid, AOP_FLAG_NOFS);
+	page = grab_cache_page(NODE_MAPPING(sbi), dn->nid);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -867,6 +882,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	new_ni.ino = dn->inode->i_ino;
 	set_node_addr(sbi, &new_ni, NEW_ADDR, false);
 
+	f2fs_wait_on_page_writeback(page, NODE);
 	fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
 	set_cold_node(dn->inode, page);
 	SetPageUptodate(page);
@@ -946,8 +962,7 @@ struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
 	struct page *page;
 	int err;
 repeat:
-	page = grab_cache_page_write_begin(NODE_MAPPING(sbi),
-					nid, AOP_FLAG_NOFS);
+	page = grab_cache_page(NODE_MAPPING(sbi), nid);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -1194,6 +1209,8 @@ static int f2fs_write_node_page(struct page *page,
 		.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
 	};
 
+	trace_f2fs_writepage(page, NODE);
+
 	if (unlikely(sbi->por_doing))
 		goto redirty_out;
 
@@ -1225,10 +1242,7 @@ static int f2fs_write_node_page(struct page *page,
 	return 0;
 
 redirty_out:
-	dec_page_count(sbi, F2FS_DIRTY_NODES);
-	wbc->pages_skipped++;
-	account_page_redirty(page);
-	set_page_dirty(page);
+	redirty_page_for_writepage(wbc, page);
 	return AOP_WRITEPAGE_ACTIVATE;
 }
 
@@ -1238,6 +1252,8 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
 	long diff;
 
+	trace_f2fs_writepages(mapping->host, wbc, NODE);
+
 	/* balancing f2fs's metadata in background */
 	f2fs_balance_fs_bg(sbi);
 
@@ -1313,13 +1329,14 @@ static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i,
 	radix_tree_delete(&nm_i->free_nid_root, i->nid);
 }
 
-static int add_free_nid(struct f2fs_nm_info *nm_i, nid_t nid, bool build)
+static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i;
 	struct nat_entry *ne;
 	bool allocated = false;
 
-	if (!available_free_memory(nm_i, FREE_NIDS))
+	if (!available_free_memory(sbi, FREE_NIDS))
 		return -1;
 
 	/* 0 nid should not be used */
@@ -1372,9 +1389,10 @@ static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
 		kmem_cache_free(free_nid_slab, i);
 }
 
-static void scan_nat_page(struct f2fs_nm_info *nm_i,
+static void scan_nat_page(struct f2fs_sb_info *sbi,
 			struct page *nat_page, nid_t start_nid)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct f2fs_nat_block *nat_blk = page_address(nat_page);
 	block_t blk_addr;
 	int i;
@@ -1389,7 +1407,7 @@ static void scan_nat_page(struct f2fs_nm_info *nm_i,
 		blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
 		f2fs_bug_on(blk_addr == NEW_ADDR);
 		if (blk_addr == NULL_ADDR) {
-			if (add_free_nid(nm_i, start_nid, true) < 0)
+			if (add_free_nid(sbi, start_nid, true) < 0)
 				break;
 		}
 	}
@@ -1413,7 +1431,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 	while (1) {
 		struct page *page = get_current_nat_page(sbi, nid);
 
-		scan_nat_page(nm_i, page, nid);
+		scan_nat_page(sbi, page, nid);
 		f2fs_put_page(page, 1);
 
 		nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK));
@@ -1433,7 +1451,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 		block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr);
 		nid = le32_to_cpu(nid_in_journal(sum, i));
 		if (addr == NULL_ADDR)
-			add_free_nid(nm_i, nid, true);
+			add_free_nid(sbi, nid, true);
 		else
 			remove_free_nid(nm_i, nid);
 	}
@@ -1450,7 +1468,7 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i = NULL;
 retry:
-	if (unlikely(sbi->total_valid_node_count + 1 >= nm_i->max_nid))
+	if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids))
 		return false;
 
 	spin_lock(&nm_i->free_nid_list_lock);
@@ -1510,7 +1528,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
 	spin_lock(&nm_i->free_nid_list_lock);
 	i = __lookup_free_nid_list(nm_i, nid);
 	f2fs_bug_on(!i || i->state != NID_ALLOC);
-	if (!available_free_memory(nm_i, FREE_NIDS)) {
+	if (!available_free_memory(sbi, FREE_NIDS)) {
 		__del_from_free_nid_list(nm_i, i);
 		need_free = true;
 	} else {
@@ -1532,7 +1550,7 @@ void recover_node_page(struct f2fs_sb_info *sbi, struct page *page,
 	clear_node_page_dirty(page);
 }
 
-void recover_inline_xattr(struct inode *inode, struct page *page)
+static void recover_inline_xattr(struct inode *inode, struct page *page)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	void *src_addr, *dst_addr;
@@ -1557,6 +1575,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
 	src_addr = inline_xattr_addr(page);
 	inline_size = inline_xattr_size(inode);
 
+	f2fs_wait_on_page_writeback(ipage, NODE);
 	memcpy(dst_addr, src_addr, inline_size);
 
 	update_inode(inode, ipage);
@@ -1612,6 +1631,11 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	struct node_info old_ni, new_ni;
 	struct page *ipage;
 
+	get_node_info(sbi, ino, &old_ni);
+
+	if (unlikely(old_ni.blk_addr != NULL_ADDR))
+		return -EINVAL;
+
 	ipage = grab_cache_page(NODE_MAPPING(sbi), ino);
 	if (!ipage)
 		return -ENOMEM;
@@ -1619,7 +1643,6 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	/* Should not use this inode  from free nid list */
 	remove_free_nid(NM_I(sbi), ino);
 
-	get_node_info(sbi, ino, &old_ni);
 	SetPageUptodate(ipage);
 	fill_node_footer(ipage, ino, ino, 0, true);
 
@@ -1645,35 +1668,29 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 
 /*
  * ra_sum_pages() merge contiguous pages into one bio and submit.
- * these pre-readed pages are linked in pages list.
+ * these pre-readed pages are alloced in bd_inode's mapping tree.
  */
-static int ra_sum_pages(struct f2fs_sb_info *sbi, struct list_head *pages,
+static int ra_sum_pages(struct f2fs_sb_info *sbi, struct page **pages,
 				int start, int nrpages)
 {
-	struct page *page;
-	int page_idx = start;
+	struct inode *inode = sbi->sb->s_bdev->bd_inode;
+	struct address_space *mapping = inode->i_mapping;
+	int i, page_idx = start;
 	struct f2fs_io_info fio = {
 		.type = META,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO
 	};
 
-	for (; page_idx < start + nrpages; page_idx++) {
-		/* alloc temporal page for read node summary info*/
-		page = alloc_page(GFP_F2FS_ZERO);
-		if (!page)
+	for (i = 0; page_idx < start + nrpages; page_idx++, i++) {
+		/* alloc page in bd_inode for reading node summary info */
+		pages[i] = grab_cache_page(mapping, page_idx);
+		if (!pages[i])
 			break;
-
-		lock_page(page);
-		page->index = page_idx;
-		list_add_tail(&page->lru, pages);
+		f2fs_submit_page_mbio(sbi, pages[i], page_idx, &fio);
 	}
 
-	list_for_each_entry(page, pages, lru)
-		f2fs_submit_page_mbio(sbi, page, page->index, &fio);
-
 	f2fs_submit_merged_bio(sbi, META, READ);
-
-	return page_idx - start;
+	return i;
 }
 
 int restore_node_summary(struct f2fs_sb_info *sbi,
@@ -1681,11 +1698,11 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
 {
 	struct f2fs_node *rn;
 	struct f2fs_summary *sum_entry;
-	struct page *page, *tmp;
+	struct inode *inode = sbi->sb->s_bdev->bd_inode;
 	block_t addr;
 	int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
-	int i, last_offset, nrpages, err = 0;
-	LIST_HEAD(page_list);
+	struct page *pages[bio_blocks];
+	int i, idx, last_offset, nrpages, err = 0;
 
 	/* scan the node segment */
 	last_offset = sbi->blocks_per_seg;
@@ -1696,29 +1713,31 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
 		nrpages = min(last_offset - i, bio_blocks);
 
 		/* read ahead node pages */
-		nrpages = ra_sum_pages(sbi, &page_list, addr, nrpages);
+		nrpages = ra_sum_pages(sbi, pages, addr, nrpages);
 		if (!nrpages)
 			return -ENOMEM;
 
-		list_for_each_entry_safe(page, tmp, &page_list, lru) {
+		for (idx = 0; idx < nrpages; idx++) {
 			if (err)
 				goto skip;
 
-			lock_page(page);
-			if (unlikely(!PageUptodate(page))) {
+			lock_page(pages[idx]);
+			if (unlikely(!PageUptodate(pages[idx]))) {
 				err = -EIO;
 			} else {
-				rn = F2FS_NODE(page);
+				rn = F2FS_NODE(pages[idx]);
 				sum_entry->nid = rn->footer.nid;
 				sum_entry->version = 0;
 				sum_entry->ofs_in_node = 0;
 				sum_entry++;
 			}
-			unlock_page(page);
+			unlock_page(pages[idx]);
 skip:
-			list_del(&page->lru);
-			__free_pages(page, 0);
+			page_cache_release(pages[idx]);
 		}
+
+		invalidate_mapping_pages(inode->i_mapping, addr,
+							addr + nrpages);
 	}
 	return err;
 }
@@ -1756,9 +1775,7 @@ retry:
 			write_unlock(&nm_i->nat_tree_lock);
 			goto retry;
 		}
-		nat_set_blkaddr(ne, le32_to_cpu(raw_ne.block_addr));
-		nat_set_ino(ne, le32_to_cpu(raw_ne.ino));
-		nat_set_version(ne, raw_ne.version);
+		node_info_from_raw_nat(&ne->ni, &raw_ne);
 		__set_nat_cache_dirty(nm_i, ne);
 		write_unlock(&nm_i->nat_tree_lock);
 	}
@@ -1791,7 +1808,6 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 		nid_t nid;
 		struct f2fs_nat_entry raw_ne;
 		int offset = -1;
-		block_t new_blkaddr;
 
 		if (nat_get_blkaddr(ne) == NEW_ADDR)
 			continue;
@@ -1827,11 +1843,7 @@ to_nat_page:
 		f2fs_bug_on(!nat_blk);
 		raw_ne = nat_blk->entries[nid - start_nid];
 flush_now:
-		new_blkaddr = nat_get_blkaddr(ne);
-
-		raw_ne.ino = cpu_to_le32(nat_get_ino(ne));
-		raw_ne.block_addr = cpu_to_le32(new_blkaddr);
-		raw_ne.version = nat_get_version(ne);
+		raw_nat_from_node_info(&raw_ne, &ne->ni);
 
 		if (offset < 0) {
 			nat_blk->entries[nid - start_nid] = raw_ne;
@@ -1841,7 +1853,7 @@ flush_now:
 		}
 
 		if (nat_get_blkaddr(ne) == NULL_ADDR &&
-				add_free_nid(NM_I(sbi), nid, false) <= 0) {
+				add_free_nid(sbi, nid, false) <= 0) {
 			write_lock(&nm_i->nat_tree_lock);
 			__del_from_nat_cache(nm_i, ne);
 			write_unlock(&nm_i->nat_tree_lock);
@@ -1869,8 +1881,10 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1;
 	nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
 
+	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks;
+
 	/* not used nids: 0, node, meta, (and root counted as valid node) */
-	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks - 3;
+	nm_i->available_nids = nm_i->max_nid - 3;
 	nm_i->fcnt = 0;
 	nm_i->nat_cnt = 0;
 	nm_i->ram_thresh = DEF_RAM_THRESHOLD;

fs/f2fs/node.h

@@ -59,12 +59,12 @@ struct nat_entry {
 	do {								\
 		ne->checkpointed = false;				\
 		list_move_tail(&ne->list, &nm_i->dirty_nat_entries);	\
-	} while (0);
+	} while (0)
 #define __clear_nat_cache_dirty(nm_i, ne)				\
 	do {								\
 		ne->checkpointed = true;				\
 		list_move_tail(&ne->list, &nm_i->nat_entries);		\
-	} while (0);
+	} while (0)
 #define inc_node_version(version)	(++version)
 
 static inline void node_info_from_raw_nat(struct node_info *ni,
@@ -75,9 +75,18 @@ static inline void node_info_from_raw_nat(struct node_info *ni,
 	ni->version = raw_ne->version;
 }
 
-enum nid_type {
+static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
+						struct node_info *ni)
+{
+	raw_ne->ino = cpu_to_le32(ni->ino);
+	raw_ne->block_addr = cpu_to_le32(ni->blk_addr);
+	raw_ne->version = ni->version;
+}
+
+enum mem_type {
 	FREE_NIDS,	/* indicates the free nid list */
-	NAT_ENTRIES	/* indicates the cached nat entry */
+	NAT_ENTRIES,	/* indicates the cached nat entry */
+	DIRTY_DENTS	/* indicates dirty dentry pages */
 };
 
 /*
@@ -263,7 +272,7 @@ static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
 {
 	struct f2fs_node *rn = F2FS_NODE(p);
 
-	wait_on_page_writeback(p);
+	f2fs_wait_on_page_writeback(p, NODE);
 
 	if (i)
 		rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);

fs/f2fs/recovery.c

@@ -46,15 +46,10 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
 	struct inode *dir, *einode;
 	int err = 0;
 
-	dir = check_dirty_dir_inode(F2FS_SB(inode->i_sb), pino);
-	if (!dir) {
-		dir = f2fs_iget(inode->i_sb, pino);
-		if (IS_ERR(dir)) {
-			err = PTR_ERR(dir);
-			goto out;
-		}
-		set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
-		add_dirty_dir_inode(dir);
+	dir = f2fs_iget(inode->i_sb, pino);
+	if (IS_ERR(dir)) {
+		err = PTR_ERR(dir);
+		goto out;
 	}
 
 	name.len = le32_to_cpu(raw_inode->i_namelen);
@@ -63,7 +58,7 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
 	if (unlikely(name.len > F2FS_NAME_LEN)) {
 		WARN_ON(1);
 		err = -ENAMETOOLONG;
-		goto out;
+		goto out_err;
 	}
 retry:
 	de = f2fs_find_entry(dir, &name, &page);
@@ -73,7 +68,8 @@ retry:
 		einode = f2fs_iget(inode->i_sb, le32_to_cpu(de->ino));
 		if (IS_ERR(einode)) {
 			WARN_ON(1);
-			if (PTR_ERR(einode) == -ENOENT)
+			err = PTR_ERR(einode);
+			if (err == -ENOENT)
 				err = -EEXIST;
 			goto out_unmap_put;
 		}
@@ -87,11 +83,23 @@ retry:
 		goto retry;
 	}
 	err = __f2fs_add_link(dir, &name, inode);
+	if (err)
+		goto out_err;
+
+	if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) {
+		iput(dir);
+	} else {
+		add_dirty_dir_inode(dir);
+		set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
+	}
+
 	goto out;
 
 out_unmap_put:
 	kunmap(page);
 	f2fs_put_page(page, 0);
+out_err:
+	iput(dir);
 out:
 	f2fs_msg(inode->i_sb, KERN_NOTICE,
 			"%s: ino = %x, name = %s, dir = %lx, err = %d",
@@ -299,10 +307,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 		goto out;
 
 	start = start_bidx_of_node(ofs_of_node(page), fi);
-	if (IS_INODE(page))
-		end = start + ADDRS_PER_INODE(fi);
-	else
-		end = start + ADDRS_PER_BLOCK;
+	end = start + ADDRS_PER_PAGE(page, fi);
 
 	f2fs_lock_op(sbi);
 

fs/f2fs/segment.c

@@ -25,7 +25,6 @@
 #define __reverse_ffz(x) __reverse_ffs(~(x))
 
 static struct kmem_cache *discard_entry_slab;
-static struct kmem_cache *flush_cmd_slab;
 
 /*
  * __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since
@@ -200,20 +199,20 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 static int issue_flush_thread(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
-	struct f2fs_sm_info *sm_i = SM_I(sbi);
-	wait_queue_head_t *q = &sm_i->flush_wait_queue;
+	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+	wait_queue_head_t *q = &fcc->flush_wait_queue;
 repeat:
 	if (kthread_should_stop())
 		return 0;
 
-	spin_lock(&sm_i->issue_lock);
-	if (sm_i->issue_list) {
-		sm_i->dispatch_list = sm_i->issue_list;
-		sm_i->issue_list = sm_i->issue_tail = NULL;
+	spin_lock(&fcc->issue_lock);
+	if (fcc->issue_list) {
+		fcc->dispatch_list = fcc->issue_list;
+		fcc->issue_list = fcc->issue_tail = NULL;
 	}
-	spin_unlock(&sm_i->issue_lock);
+	spin_unlock(&fcc->issue_lock);
 
-	if (sm_i->dispatch_list) {
+	if (fcc->dispatch_list) {
 		struct bio *bio = bio_alloc(GFP_NOIO, 0);
 		struct flush_cmd *cmd, *next;
 		int ret;
@@ -221,47 +220,79 @@ repeat:
 		bio->bi_bdev = sbi->sb->s_bdev;
 		ret = submit_bio_wait(WRITE_FLUSH, bio);
 
-		for (cmd = sm_i->dispatch_list; cmd; cmd = next) {
+		for (cmd = fcc->dispatch_list; cmd; cmd = next) {
 			cmd->ret = ret;
 			next = cmd->next;
 			complete(&cmd->wait);
 		}
-		sm_i->dispatch_list = NULL;
+		bio_put(bio);
+		fcc->dispatch_list = NULL;
 	}
 
-	wait_event_interruptible(*q, kthread_should_stop() || sm_i->issue_list);
+	wait_event_interruptible(*q,
+			kthread_should_stop() || fcc->issue_list);
 	goto repeat;
 }
 
 int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 {
-	struct f2fs_sm_info *sm_i = SM_I(sbi);
-	struct flush_cmd *cmd;
-	int ret;
+	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+	struct flush_cmd cmd;
 
 	if (!test_opt(sbi, FLUSH_MERGE))
 		return blkdev_issue_flush(sbi->sb->s_bdev, GFP_KERNEL, NULL);
 
-	cmd = f2fs_kmem_cache_alloc(flush_cmd_slab, GFP_ATOMIC);
-	cmd->next = NULL;
-	cmd->ret = 0;
-	init_completion(&cmd->wait);
+	init_completion(&cmd.wait);
+	cmd.next = NULL;
 
-	spin_lock(&sm_i->issue_lock);
-	if (sm_i->issue_list)
-		sm_i->issue_tail->next = cmd;
+	spin_lock(&fcc->issue_lock);
+	if (fcc->issue_list)
+		fcc->issue_tail->next = &cmd;
 	else
-		sm_i->issue_list = cmd;
-	sm_i->issue_tail = cmd;
-	spin_unlock(&sm_i->issue_lock);
+		fcc->issue_list = &cmd;
+	fcc->issue_tail = &cmd;
+	spin_unlock(&fcc->issue_lock);
 
-	if (!sm_i->dispatch_list)
-		wake_up(&sm_i->flush_wait_queue);
+	if (!fcc->dispatch_list)
+		wake_up(&fcc->flush_wait_queue);
 
-	wait_for_completion(&cmd->wait);
-	ret = cmd->ret;
-	kmem_cache_free(flush_cmd_slab, cmd);
-	return ret;
+	wait_for_completion(&cmd.wait);
+
+	return cmd.ret;
+}
+
+int create_flush_cmd_control(struct f2fs_sb_info *sbi)
+{
+	dev_t dev = sbi->sb->s_bdev->bd_dev;
+	struct flush_cmd_control *fcc;
+	int err = 0;
+
+	fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
+	if (!fcc)
+		return -ENOMEM;
+	spin_lock_init(&fcc->issue_lock);
+	init_waitqueue_head(&fcc->flush_wait_queue);
+	fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
+				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
+	if (IS_ERR(fcc->f2fs_issue_flush)) {
+		err = PTR_ERR(fcc->f2fs_issue_flush);
+		kfree(fcc);
+		return err;
+	}
+	sbi->sm_info->cmd_control_info = fcc;
+
+	return err;
+}
+
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi)
+{
+	struct flush_cmd_control *fcc =
+				sbi->sm_info->cmd_control_info;
+
+	if (fcc && fcc->f2fs_issue_flush)
+		kthread_stop(fcc->f2fs_issue_flush);
+	kfree(fcc);
+	sbi->sm_info->cmd_control_info = NULL;
 }
 
 static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
@@ -336,13 +367,26 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
 	mutex_unlock(&dirty_i->seglist_lock);
 }
 
-static void f2fs_issue_discard(struct f2fs_sb_info *sbi,
+static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 				block_t blkstart, block_t blklen)
 {
 	sector_t start = SECTOR_FROM_BLOCK(sbi, blkstart);
 	sector_t len = SECTOR_FROM_BLOCK(sbi, blklen);
-	blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
 	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
+	return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
+}
+
+void discard_next_dnode(struct f2fs_sb_info *sbi)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
+	block_t blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+
+	if (f2fs_issue_discard(sbi, blkaddr, 1)) {
+		struct page *page = grab_meta_page(sbi, blkaddr);
+		/* zero-filled page */
+		set_page_dirty(page);
+		f2fs_put_page(page, 1);
+	}
 }
 
 static void add_discard_addrs(struct f2fs_sb_info *sbi,
@@ -1832,7 +1876,6 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	dev_t dev = sbi->sb->s_bdev->bd_dev;
 	struct f2fs_sm_info *sm_info;
 	int err;
 
@@ -1860,14 +1903,10 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->nr_discards = 0;
 	sm_info->max_discards = 0;
 
-	if (test_opt(sbi, FLUSH_MERGE)) {
-		spin_lock_init(&sm_info->issue_lock);
-		init_waitqueue_head(&sm_info->flush_wait_queue);
-
-		sm_info->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
-				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
-		if (IS_ERR(sm_info->f2fs_issue_flush))
-			return PTR_ERR(sm_info->f2fs_issue_flush);
+	if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
+		err = create_flush_cmd_control(sbi);
+		if (err)
+			return err;
 	}
 
 	err = build_sit_info(sbi);
@@ -1976,10 +2015,10 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 void destroy_segment_manager(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_sm_info *sm_info = SM_I(sbi);
+
 	if (!sm_info)
 		return;
-	if (sm_info->f2fs_issue_flush)
-		kthread_stop(sm_info->f2fs_issue_flush);
+	destroy_flush_cmd_control(sbi);
 	destroy_dirty_segmap(sbi);
 	destroy_curseg(sbi);
 	destroy_free_segmap(sbi);
@@ -1994,17 +2033,10 @@ int __init create_segment_manager_caches(void)
 			sizeof(struct discard_entry));
 	if (!discard_entry_slab)
 		return -ENOMEM;
-	flush_cmd_slab = f2fs_kmem_cache_create("flush_command",
-			sizeof(struct flush_cmd));
-	if (!flush_cmd_slab) {
-		kmem_cache_destroy(discard_entry_slab);
-		return -ENOMEM;
-	}
 	return 0;
 }
 
 void destroy_segment_manager_caches(void)
 {
 	kmem_cache_destroy(discard_entry_slab);
-	kmem_cache_destroy(flush_cmd_slab);
 }

fs/f2fs/super.c

@@ -514,7 +514,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
 
-	if (!(root->d_sb->s_flags & MS_RDONLY) && test_opt(sbi, BG_GC))
+	if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC))
 		seq_printf(seq, ",background_gc=%s", "on");
 	else
 		seq_printf(seq, ",background_gc=%s", "off");
@@ -542,7 +542,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",disable_ext_identify");
 	if (test_opt(sbi, INLINE_DATA))
 		seq_puts(seq, ",inline_data");
-	if (test_opt(sbi, FLUSH_MERGE))
+	if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE))
 		seq_puts(seq, ",flush_merge");
 	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
 
@@ -594,6 +594,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct f2fs_mount_info org_mount_opt;
 	int err, active_logs;
+	bool need_restart_gc = false;
+	bool need_stop_gc = false;
 
 	sync_filesystem(sb);
 
@@ -611,7 +613,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 
 	/*
 	 * Previous and new state of filesystem is RO,
-	 * so no point in checking GC conditions.
+	 * so skip checking GC and FLUSH_MERGE conditions.
 	 */
 	if ((sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY))
 		goto skip;
@@ -625,18 +627,40 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		if (sbi->gc_thread) {
 			stop_gc_thread(sbi);
 			f2fs_sync_fs(sb, 1);
+			need_restart_gc = true;
 		}
 	} else if (test_opt(sbi, BG_GC) && !sbi->gc_thread) {
 		err = start_gc_thread(sbi);
 		if (err)
 			goto restore_opts;
+		need_stop_gc = true;
+	}
+
+	/*
+	 * We stop issue flush thread if FS is mounted as RO
+	 * or if flush_merge is not passed in mount option.
+	 */
+	if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
+		destroy_flush_cmd_control(sbi);
+	} else if (test_opt(sbi, FLUSH_MERGE) &&
+					!sbi->sm_info->cmd_control_info) {
+		err = create_flush_cmd_control(sbi);
+		if (err)
+			goto restore_gc;
 	}
 skip:
 	/* Update the POSIXACL Flag */
 	 sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
 	return 0;
-
+restore_gc:
+	if (need_restart_gc) {
+		if (start_gc_thread(sbi))
+			f2fs_msg(sbi->sb, KERN_WARNING,
+				"background gc thread is stop");
+	} else if (need_stop_gc) {
+		stop_gc_thread(sbi);
+	}
 restore_opts:
 	sbi->mount_opt = org_mount_opt;
 	sbi->active_logs = active_logs;

fs/f2fs/xattr.c

@@ -26,7 +26,7 @@
 #include "xattr.h"
 
 static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
+		size_t list_size, const char *name, size_t len, int type)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
 	int total_len, prefix_len = 0;
@@ -53,11 +53,11 @@ static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list,
 		return -EINVAL;
 	}
 
-	total_len = prefix_len + name_len + 1;
+	total_len = prefix_len + len + 1;
 	if (list && total_len <= list_size) {
 		memcpy(list, prefix, prefix_len);
-		memcpy(list + prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
+		memcpy(list + prefix_len, name, len);
+		list[prefix_len + len] = '\0';
 	}
 	return total_len;
 }
@@ -108,11 +108,12 @@ static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name,
 	if (strcmp(name, "") == 0)
 		return -EINVAL;
 
-	return f2fs_setxattr(dentry->d_inode, type, name, value, size, NULL);
+	return f2fs_setxattr(dentry->d_inode, type, name,
+					value, size, NULL, flags);
 }
 
 static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
+		size_t list_size, const char *name, size_t len, int type)
 {
 	const char *xname = F2FS_SYSTEM_ADVISE_PREFIX;
 	size_t size;
@@ -155,9 +156,6 @@ static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name,
 }
 
 #ifdef CONFIG_F2FS_FS_SECURITY
-static int __f2fs_setxattr(struct inode *inode, int name_index,
-			const char *name, const void *value, size_t value_len,
-			struct page *ipage);
 static int f2fs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 		void *page)
 {
@@ -165,9 +163,9 @@ static int f2fs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 	int err = 0;
 
 	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
-		err = __f2fs_setxattr(inode, F2FS_XATTR_INDEX_SECURITY,
+		err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_SECURITY,
 				xattr->name, xattr->value,
-				xattr->value_len, (struct page *)page);
+				xattr->value_len, (struct page *)page, 0);
 		if (err < 0)
 			break;
 	}
@@ -241,26 +239,26 @@ const struct xattr_handler *f2fs_xattr_handlers[] = {
 	NULL,
 };
 
-static inline const struct xattr_handler *f2fs_xattr_handler(int name_index)
+static inline const struct xattr_handler *f2fs_xattr_handler(int index)
 {
 	const struct xattr_handler *handler = NULL;
 
-	if (name_index > 0 && name_index < ARRAY_SIZE(f2fs_xattr_handler_map))
-		handler = f2fs_xattr_handler_map[name_index];
+	if (index > 0 && index < ARRAY_SIZE(f2fs_xattr_handler_map))
+		handler = f2fs_xattr_handler_map[index];
 	return handler;
 }
 
-static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int name_index,
-					size_t name_len, const char *name)
+static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index,
+					size_t len, const char *name)
 {
 	struct f2fs_xattr_entry *entry;
 
 	list_for_each_xattr(entry, base_addr) {
-		if (entry->e_name_index != name_index)
+		if (entry->e_name_index != index)
 			continue;
-		if (entry->e_name_len != name_len)
+		if (entry->e_name_len != len)
 			continue;
-		if (!memcmp(entry->e_name, name, name_len))
+		if (!memcmp(entry->e_name, name, len))
 			break;
 	}
 	return entry;
@@ -347,6 +345,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 
 		if (ipage) {
 			inline_addr = inline_xattr_addr(ipage);
+			f2fs_wait_on_page_writeback(ipage, NODE);
 		} else {
 			page = get_node_page(sbi, inode->i_ino);
 			if (IS_ERR(page)) {
@@ -354,6 +353,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 				return PTR_ERR(page);
 			}
 			inline_addr = inline_xattr_addr(page);
+			f2fs_wait_on_page_writeback(page, NODE);
 		}
 		memcpy(inline_addr, txattr_addr, inline_size);
 		f2fs_put_page(page, 1);
@@ -374,6 +374,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 			return PTR_ERR(xpage);
 		}
 		f2fs_bug_on(new_nid);
+		f2fs_wait_on_page_writeback(xpage, NODE);
 	} else {
 		struct dnode_of_data dn;
 		set_new_dnode(&dn, inode, NULL, NULL, new_nid);
@@ -396,42 +397,43 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 	return 0;
 }
 
-int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
+int f2fs_getxattr(struct inode *inode, int index, const char *name,
 		void *buffer, size_t buffer_size)
 {
 	struct f2fs_xattr_entry *entry;
 	void *base_addr;
 	int error = 0;
-	size_t value_len, name_len;
+	size_t size, len;
 
 	if (name == NULL)
 		return -EINVAL;
-	name_len = strlen(name);
-	if (name_len > F2FS_NAME_LEN)
+
+	len = strlen(name);
+	if (len > F2FS_NAME_LEN)
 		return -ERANGE;
 
 	base_addr = read_all_xattrs(inode, NULL);
 	if (!base_addr)
 		return -ENOMEM;
 
-	entry = __find_xattr(base_addr, name_index, name_len, name);
+	entry = __find_xattr(base_addr, index, len, name);
 	if (IS_XATTR_LAST_ENTRY(entry)) {
 		error = -ENODATA;
 		goto cleanup;
 	}
 
-	value_len = le16_to_cpu(entry->e_value_size);
+	size = le16_to_cpu(entry->e_value_size);
 
-	if (buffer && value_len > buffer_size) {
+	if (buffer && size > buffer_size) {
 		error = -ERANGE;
 		goto cleanup;
 	}
 
 	if (buffer) {
 		char *pval = entry->e_name + entry->e_name_len;
-		memcpy(buffer, pval, value_len);
+		memcpy(buffer, pval, size);
 	}
-	error = value_len;
+	error = size;
 
 cleanup:
 	kzfree(base_addr);
@@ -475,15 +477,15 @@ cleanup:
 	return error;
 }
 
-static int __f2fs_setxattr(struct inode *inode, int name_index,
-			const char *name, const void *value, size_t value_len,
-			struct page *ipage)
+static int __f2fs_setxattr(struct inode *inode, int index,
+			const char *name, const void *value, size_t size,
+			struct page *ipage, int flags)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_xattr_entry *here, *last;
 	void *base_addr;
 	int found, newsize;
-	size_t name_len;
+	size_t len;
 	__u32 new_hsize;
 	int error = -ENOMEM;
 
@@ -491,11 +493,11 @@ static int __f2fs_setxattr(struct inode *inode, int name_index,
 		return -EINVAL;
 
 	if (value == NULL)
-		value_len = 0;
+		size = 0;
 
-	name_len = strlen(name);
+	len = strlen(name);
 
-	if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN(inode))
+	if (len > F2FS_NAME_LEN || size > MAX_VALUE_LEN(inode))
 		return -ERANGE;
 
 	base_addr = read_all_xattrs(inode, ipage);
@@ -503,16 +505,23 @@ static int __f2fs_setxattr(struct inode *inode, int name_index,
 		goto exit;
 
 	/* find entry with wanted name. */
-	here = __find_xattr(base_addr, name_index, name_len, name);
+	here = __find_xattr(base_addr, index, len, name);
 
 	found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
-	last = here;
 
+	if ((flags & XATTR_REPLACE) && !found) {
+		error = -ENODATA;
+		goto exit;
+	} else if ((flags & XATTR_CREATE) && found) {
+		error = -EEXIST;
+		goto exit;
+	}
+
+	last = here;
 	while (!IS_XATTR_LAST_ENTRY(last))
 		last = XATTR_NEXT_ENTRY(last);
 
-	newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) +
-			name_len + value_len);
+	newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + len + size);
 
 	/* 1. Check space */
 	if (value) {
@@ -555,12 +564,12 @@ static int __f2fs_setxattr(struct inode *inode, int name_index,
 		 * We just write new entry.
 		 */
 		memset(last, 0, newsize);
-		last->e_name_index = name_index;
-		last->e_name_len = name_len;
-		memcpy(last->e_name, name, name_len);
-		pval = last->e_name + name_len;
-		memcpy(pval, value, value_len);
-		last->e_value_size = cpu_to_le16(value_len);
+		last->e_name_index = index;
+		last->e_name_len = len;
+		memcpy(last->e_name, name, len);
+		pval = last->e_name + len;
+		memcpy(pval, value, size);
+		last->e_value_size = cpu_to_le16(size);
 		new_hsize += newsize;
 	}
 
@@ -583,18 +592,23 @@ exit:
 	return error;
 }
 
-int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
-			const void *value, size_t value_len, struct page *ipage)
+int f2fs_setxattr(struct inode *inode, int index, const char *name,
+				const void *value, size_t size,
+				struct page *ipage, int flags)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	int err;
 
+	/* this case is only from init_inode_metadata */
+	if (ipage)
+		return __f2fs_setxattr(inode, index, name, value,
+						size, ipage, flags);
 	f2fs_balance_fs(sbi);
 
 	f2fs_lock_op(sbi);
 	/* protect xattr_ver */
 	down_write(&F2FS_I(inode)->i_sem);
-	err = __f2fs_setxattr(inode, name_index, name, value, value_len, ipage);
+	err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags);
 	up_write(&F2FS_I(inode)->i_sem);
 	f2fs_unlock_op(sbi);
 

fs/f2fs/xattr.h

@@ -114,18 +114,18 @@ extern const struct xattr_handler f2fs_xattr_security_handler;
 extern const struct xattr_handler *f2fs_xattr_handlers[];
 
 extern int f2fs_setxattr(struct inode *, int, const char *,
-				const void *, size_t, struct page *);
+				const void *, size_t, struct page *, int);
 extern int f2fs_getxattr(struct inode *, int, const char *, void *, size_t);
 extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
 #else
 
 #define f2fs_xattr_handlers	NULL
-static inline int f2fs_setxattr(struct inode *inode, int name_index,
-		const char *name, const void *value, size_t value_len)
+static inline int f2fs_setxattr(struct inode *inode, int index,
+		const char *name, const void *value, size_t size, int flags)
 {
 	return -EOPNOTSUPP;
 }
-static inline int f2fs_getxattr(struct inode *inode, int name_index,
+static inline int f2fs_getxattr(struct inode *inode, int index,
 		const char *name, void *buffer, size_t buffer_size)
 {
 	return -EOPNOTSUPP;

include/linux/f2fs_fs.h

@@ -19,6 +19,7 @@
 #define F2FS_LOG_SECTORS_PER_BLOCK	3	/* 4KB: F2FS_BLKSIZE */
 #define F2FS_BLKSIZE			4096	/* support only 4KB block */
 #define F2FS_MAX_EXTENSION		64	/* # of extension entries */
+#define F2FS_BLK_ALIGN(x)	(((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE)
 
 #define NULL_ADDR		((block_t)0)	/* used as block_t addresses */
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
@@ -75,6 +76,7 @@ struct f2fs_super_block {
 	__le16 volume_name[512];	/* volume name */
 	__le32 extension_count;		/* # of extensions below */
 	__u8 extension_list[F2FS_MAX_EXTENSION][8];	/* extension array */
+	__le32 cp_payload;
 } __packed;
 
 /*
@@ -146,6 +148,9 @@ struct f2fs_extent {
 #define ADDRS_PER_BLOCK		1018	/* Address Pointers in a Direct Block */
 #define NIDS_PER_BLOCK		1018	/* Node IDs in an Indirect Block */
 
+#define ADDRS_PER_PAGE(page, fi)	\
+	(IS_INODE(page) ? ADDRS_PER_INODE(fi) : ADDRS_PER_BLOCK)
+
 #define	NODE_DIR1_BLOCK		(DEF_ADDRS_PER_INODE + 1)
 #define	NODE_DIR2_BLOCK		(DEF_ADDRS_PER_INODE + 2)
 #define	NODE_IND1_BLOCK		(DEF_ADDRS_PER_INODE + 3)
@@ -391,6 +396,9 @@ typedef __le32	f2fs_hash_t;
 /* MAX level for dir lookup */
 #define MAX_DIR_HASH_DEPTH	63
 
+/* MAX buckets in one level of dir */
+#define MAX_DIR_BUCKETS		(1 << ((MAX_DIR_HASH_DEPTH / 2) - 1))
+
 #define SIZE_OF_DIR_ENTRY	11	/* by byte */
 #define SIZE_OF_DENTRY_BITMAP	((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \
 					BITS_PER_BYTE)

include/trace/events/f2fs.h

@@ -659,6 +659,66 @@ DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio,
 	TP_CONDITION(bio)
 );
 
+TRACE_EVENT(f2fs_write_begin,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+				unsigned int flags),
+
+	TP_ARGS(inode, pos, len, flags),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t,	pos)
+		__field(unsigned int, len)
+		__field(unsigned int, flags)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pos	= pos;
+		__entry->len	= len;
+		__entry->flags	= flags;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, flags = %u",
+		show_dev_ino(__entry),
+		(unsigned long long)__entry->pos,
+		__entry->len,
+		__entry->flags)
+);
+
+TRACE_EVENT(f2fs_write_end,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+				unsigned int copied),
+
+	TP_ARGS(inode, pos, len, copied),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t,	pos)
+		__field(unsigned int, len)
+		__field(unsigned int, copied)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pos	= pos;
+		__entry->len	= len;
+		__entry->copied	= copied;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, copied = %u",
+		show_dev_ino(__entry),
+		(unsigned long long)__entry->pos,
+		__entry->len,
+		__entry->copied)
+);
+
 DECLARE_EVENT_CLASS(f2fs__page,
 
 	TP_PROTO(struct page *page, int type),
@@ -672,6 +732,7 @@ DECLARE_EVENT_CLASS(f2fs__page,
 		__field(int, dir)
 		__field(pgoff_t, index)
 		__field(int, dirty)
+		__field(int, uptodate)
 	),
 
 	TP_fast_assign(
@@ -681,14 +742,31 @@ DECLARE_EVENT_CLASS(f2fs__page,
 		__entry->dir	= S_ISDIR(page->mapping->host->i_mode);
 		__entry->index	= page->index;
 		__entry->dirty	= PageDirty(page);
+		__entry->uptodate = PageUptodate(page);
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu, %s, %s, index = %lu, dirty = %d",
+	TP_printk("dev = (%d,%d), ino = %lu, %s, %s, index = %lu, "
+		"dirty = %d, uptodate = %d",
 		show_dev_ino(__entry),
 		show_block_type(__entry->type),
 		show_file_type(__entry->dir),
 		(unsigned long)__entry->index,
-		__entry->dirty)
+		__entry->dirty,
+		__entry->uptodate)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_writepage,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_readpage,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
 );
 
 DEFINE_EVENT(f2fs__page, f2fs_set_page_dirty,
@@ -705,6 +783,70 @@ DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite,
 	TP_ARGS(page, type)
 );
 
+TRACE_EVENT(f2fs_writepages,
+
+	TP_PROTO(struct inode *inode, struct writeback_control *wbc, int type),
+
+	TP_ARGS(inode, wbc, type),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(int,	type)
+		__field(int,	dir)
+		__field(long,	nr_to_write)
+		__field(long,	pages_skipped)
+		__field(loff_t,	range_start)
+		__field(loff_t,	range_end)
+		__field(pgoff_t, writeback_index)
+		__field(int,	sync_mode)
+		__field(char,	for_kupdate)
+		__field(char,	for_background)
+		__field(char,	tagged_writepages)
+		__field(char,	for_reclaim)
+		__field(char,	range_cyclic)
+		__field(char,	for_sync)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->type		= type;
+		__entry->dir		= S_ISDIR(inode->i_mode);
+		__entry->nr_to_write	= wbc->nr_to_write;
+		__entry->pages_skipped	= wbc->pages_skipped;
+		__entry->range_start	= wbc->range_start;
+		__entry->range_end	= wbc->range_end;
+		__entry->writeback_index = inode->i_mapping->writeback_index;
+		__entry->sync_mode	= wbc->sync_mode;
+		__entry->for_kupdate	= wbc->for_kupdate;
+		__entry->for_background	= wbc->for_background;
+		__entry->tagged_writepages	= wbc->tagged_writepages;
+		__entry->for_reclaim	= wbc->for_reclaim;
+		__entry->range_cyclic	= wbc->range_cyclic;
+		__entry->for_sync	= wbc->for_sync;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, %s, %s, nr_to_write %ld, "
+		"skipped %ld, start %lld, end %lld, wb_idx %lu, sync_mode %d, "
+		"kupdate %u background %u tagged %u reclaim %u cyclic %u sync %u",
+		show_dev_ino(__entry),
+		show_block_type(__entry->type),
+		show_file_type(__entry->dir),
+		__entry->nr_to_write,
+		__entry->pages_skipped,
+		__entry->range_start,
+		__entry->range_end,
+		(unsigned long)__entry->writeback_index,
+		__entry->sync_mode,
+		__entry->for_kupdate,
+		__entry->for_background,
+		__entry->tagged_writepages,
+		__entry->for_reclaim,
+		__entry->range_cyclic,
+		__entry->for_sync)
+);
+
 TRACE_EVENT(f2fs_submit_page_mbio,
 
 	TP_PROTO(struct page *page, int rw, int type, block_t blk_addr),